LMFormer: Lane based Motion Prediction Transformer

• URL: http://arxiv.org/abs/2504.10275v1
• Date: Mon, 14 Apr 2025 14:43:46 GMT
• Title: LMFormer: Lane based Motion Prediction Transformer
• Authors: Harsh Yadav, Maximilian Schaefer, Kun Zhao, Tobias Meisen,
• Abstract summary: This study presents LMFormer, a lane-aware transformer network for trajectory prediction tasks.<n>We provide a simple mechanism to dynamically prioritize the lanes and show that such a mechanism introduces explainability into the learning behavior of the network.<n>For benchmarking, we evaluate LMFormer on the nuScenes dataset and demonstrate that it achieves SOTA performance across multiple metrics.
• Score: 4.9349065371630045
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Motion prediction plays an important role in autonomous driving. This study presents LMFormer, a lane-aware transformer network for trajectory prediction tasks. In contrast to previous studies, our work provides a simple mechanism to dynamically prioritize the lanes and shows that such a mechanism introduces explainability into the learning behavior of the network. Additionally, LMFormer uses the lane connection information at intersections, lane merges, and lane splits, in order to learn long-range dependency in lane structure. Moreover, we also address the issue of refining the predicted trajectories and propose an efficient method for iterative refinement through stacked transformer layers. For benchmarking, we evaluate LMFormer on the nuScenes dataset and demonstrate that it achieves SOTA performance across multiple metrics. Furthermore, the Deep Scenario dataset is used to not only illustrate cross-dataset network performance but also the unification capabilities of LMFormer to train on multiple datasets and achieve better performance.

Related papers

• Exploring Transformer-Augmented LSTM for Temporal and Spatial Feature Learning in Trajectory Prediction [1.7273380623090846]
  This work explores the integration of Transformer based model with Long Short-Term Memory (LSTM) based technique.<n>The proposed model is benchmarked against predecessor LSTM based methods, including STA-LSTM, SA-LSTM, CS-LSTM, and NaiveLSTM.
  arXiv  Detail & Related papers  (2024-12-18T01:31:08Z)
• Enhancing Lane Segment Perception and Topology Reasoning with Crowdsourcing Trajectory Priors [12.333249510969289]
  We investigate prior augmentation from a novel perspective of trajectory priors.<n>We design a confidence-based fusion module that takes alignment into account during the fusion process.<n>Results indicate that our method's performance significantly outperforms the current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-26T07:05:05Z)
• Strada-LLM: Graph LLM for traffic prediction [62.2015839597764]
  A considerable challenge in traffic prediction lies in handling the diverse data distributions caused by vastly different traffic conditions.<n>We propose a graph-aware LLM for traffic prediction that considers proximal traffic information.<n>We adopt a lightweight approach for efficient domain adaptation when facing new data distributions in few-shot fashion.
  arXiv  Detail & Related papers  (2024-10-28T09:19:29Z)
• Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models [12.687494201105066]
  This paper proposes Traj-LLM, the first to investigate the potential of using Large Language Models (LLMs) to generate future motion from agents' past/observed trajectories and scene semantics. LLMs' powerful comprehension abilities capture a spectrum of high-level scene knowledge and interactive information. Emulating the human-like lane focus cognitive function, we introduce lane-aware probabilistic learning powered by the pioneering Mamba module.
  arXiv  Detail & Related papers  (2024-05-08T09:28:04Z)
• Pre-training on Synthetic Driving Data for Trajectory Prediction [61.520225216107306]
  We propose a pipeline-level solution to mitigate the issue of data scarcity in trajectory forecasting. We adopt HD map augmentation and trajectory synthesis for generating driving data, and then we learn representations by pre-training on them. We conduct extensive experiments to demonstrate the effectiveness of our data expansion and pre-training strategies.
  arXiv  Detail & Related papers  (2023-09-18T19:49:22Z)
• A spatial-temporal short-term traffic flow prediction model based on dynamical-learning graph convolution mechanism [0.0]
  Short-term traffic flow prediction is a vital branch of the Intelligent Traffic System (ITS) and plays an important role in traffic management. Graph convolution network (GCN) is widely used in traffic prediction models to better deal with the graphical structure data of road networks. To deal with this drawback, this paper proposes a novel location graph convolutional network (Location-GCN)
  arXiv  Detail & Related papers  (2022-05-10T09:19:12Z)
• Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design [68.1682448368636]
  We present a supervised pretraining approach to learn circuit representations that can be adapted to new unseen topologies or unseen prediction tasks. To cope with the variable topological structure of different circuits we describe each circuit as a graph and use graph neural networks (GNNs) to learn node embeddings. We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties.
  arXiv  Detail & Related papers  (2022-03-29T21:18:47Z)
• Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [54.55281692768765]
  Transformer-based supervised pre-training achieves great performance in person re-identification (ReID) Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance. This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
  arXiv  Detail & Related papers  (2021-11-23T18:59:08Z)
• Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction [71.97877759413272]
  Trajectory prediction is a safety-critical tool for autonomous vehicles to plan and execute actions. Recent methods have achieved strong performances using Multi-Choice Learning objectives like winner-takes-all (WTA) or best-of-many. Our work addresses two key challenges in trajectory prediction, learning outputs, and better predictions by imposing constraints using driving knowledge.
  arXiv  Detail & Related papers  (2021-04-16T17:58:56Z)
• A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN [59.57221522897815]
  We propose a neural network model based on trajectories information for driving behavior recognition. We evaluate the proposed model on the public BLVD dataset, achieving a satisfying performance.
  arXiv  Detail & Related papers  (2021-03-01T06:47:29Z)
• Federated Learning in Vehicular Networks [41.89469856322786]
  Federated learning (FL) framework has been introduced as an efficient tool with the goal of reducing transmission overhead. In this paper, we investigate the usage of FL over centralized learning (CL) in vehicular network applications to develop intelligent transportation systems. We identify the major challenges from both learning perspective, i.e., data labeling and model training, and from the communications point of view, i.e., data rate, reliability, transmission overhead, privacy and resource management.
  arXiv  Detail & Related papers  (2020-06-02T06:32:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.